Chollet: Test-time scaling has two axes: agent depth and breadth
fchollet · x · 2026-09-01
François Chollet notes that test-time scaling operates on two axes: running agents over longer timeframes (depth) and running a larger number of agents (breadth). While the first is widely known, the second is equally critical for solving hard problems requiring broad search.
More from AGI Musings
- Opinion: Anthropomorphizing Obscures the Distinction Between Imitation and Strategic Behavior — sebkrier · 2026-09-01
- Don't anthropomorphize AI: it shifts blame from companies — tedmitew · 2026-09-01
- Sean O'Heigeartaigh: We Must Draw a Red Line Against Agent 'Neuralese' — S_OhEigeartaigh · 2026-09-01
- Questioning AGI Definition: Why Manual Instructions Needed? — max_paperclips · 2026-09-01
- First AI Civilization May Emerge From Agent Interaction — VraserX · 2026-09-01
- Scott Alexander Refutes AI Alignment "Patching" With Hell Fable — Astral Codex Ten · 2026-09-01